Technical Program
MLSP-L3: Deep Learning II |
Session Type: Lecture |
Time: Wednesday, March 8, 08:30 - 10:30 |
Location: Grand Salon 3 |
Session Chair: David J. Miller, The Pennsylvania State University |
MLSP-L3.1: PART-LEVEL FULLY CONVOLUTIONAL NETWORKS FOR PEDESTRIAN DETECTION |
Xinran Wang; Xidian University |
Cheolkon Jung; Xidian University |
Alfred O. Hero; University of Michigan |
MLSP-L3.2: LEARNING TO INVERT: SIGNAL RECOVERY VIA DEEP CONVOLUTIONAL NETWORKS |
Ali Mousavi; Rice University |
Richard Baraniuk; Rice University |
MLSP-L3.3: STRUCTURED DROPOUT FOR WEAK LABEL AND MULTI-INSTANCE LEARNING AND ITS APPLICATION TO SCORE-INFORMED SOURCE SEPARATION |
Sebastian Ewert; Queen Mary University of London |
Mark B. Sandler; Queen Mary University of London |
MLSP-L3.4: HARNESSING NEURAL NETWORKS: A RANDOM MATRIX APPROACH |
Cosme Louart; CentraleSupélec |
Romain Couillet; CentraleSupélec |
MLSP-L3.5: TRAINING VARIANCE AND PERFORMANCE EVALUATION OF NEURAL NETWORKS IN SPEECH |
Ewout van den Berg; IBM Watson Group |
Bhuvana Ramabhadran; IBM Watson Group |
Michael Picheny; IBM Watson Group |
MLSP-L3.6: A DEEP LEARNING APPROACH TO MULTIPLE KERNEL FUSION |
Huan Song; Arizona State University |
Jayaraman J. Thiagarajan; Lawrence Livermore National Labs |
Prasanna Sattigeri; IBM T.J. Watson Research Center |
Karthikeyan Natesan Ramamurthy; IBM T.J. Watson Research Center |
Andreas Spanias; Arizona State University |